Mapping SNOMED Codes with Their Corresponding ICDO Codes - Pipeline

Description

This pipeline maps SNOMED codes to their corresponding ICDO codes via a direct dictionary lookup.

Wraps the snomed_icdo_mapper_20260901 mapper, trained on SNOMED CT US Edition 20260901 crosswalk data.

Live Demo Open in Colab Copy S3 URI

How to use


from sparknlp.pretrained import PretrainedPipeline

snomed_pipeline = PretrainedPipeline("snomed_icdo_mapping_pipeline_20260901", "en", "clinical/models")

data = spark.createDataFrame([["10013000"]]).toDF("text")
result = snomed_pipeline.transform(data)


from johnsnowlabs import nlp, medical

snomed_pipeline = nlp.PretrainedPipeline("snomed_icdo_mapping_pipeline_20260901", "en", "clinical/models")

data = spark.createDataFrame([["10013000"]]).toDF("text")
result = snomed_pipeline.transform(data)


import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline

val snomed_pipeline = PretrainedPipeline("snomed_icdo_mapping_pipeline_20260901", "en", "clinical/models")

val data = Seq("10013000").toDF("text")
val result = snomed_pipeline.transform(data)

Results

|   snomed_code | icdo_code   | all_k_resolutions   |
|--------------:|:------------|:--------------------|
|      10013000 | C40.2       | C40.2:::            |
|     102291007 | C49.2       | C49.2:::C49.5       |
|     128501000 | C49.5       | C49.5:::C76.3       |

Model Information

Model Name: snomed_icdo_mapping_pipeline_20260901
Type: pipeline
Compatibility: Healthcare NLP 6.4.1+
License: Licensed
Edition: Official
Language: en
Size: 275.7 KB

Included Models

  • DocumentAssembler
  • Doc2Chunk
  • ChunkMapperModel